Background: Protein stabilities can be affected sometimes by point mutations introduced to the protein. Current sequence-information-based protein stability prediction encoding schemes of machine learning approaches include sparse encoding and amino acid property encoding. Property encoding schemes employ physical-chemical information of the mutated protein environments, however, they produce complexity in the mean time when many properties joined in the scheme. The complexity introduces noises that affect machine learning algorithm accuracies. In order to overcome the problem we described a new encoding scheme that graded twenty amino acids into groups according to their specific property values. Results: We employed three predefined values, 0.1, 0.5, and 0.9 to represent 'weak', 'middle', and 'strong' groups for each amino acid property, and introduced two thresholds for each property to split twenty amino acids into one of the three groups according to their property values. Each amino acid can take only one out of three predefined values rather than twenty different values for each property. The complexity and noises in the encoding schemes were reduced in this way. More than 7% average accuracy improvement was found in the graded amino acid property encoding schemes by 20-fold cross validation. The overall accuracy of our method is more than 72% when performed on the independent test sets starting from sequence information with three-state prediction definitions. Conclusions: Grading numeric values of amino acid property can reduce the noises and complexity of input information. It is in accordance with biochemical concepts for amino acid properties and makes the input data simplified in the mean time. The idea of graded property encoding schemes may be applied to protein related predictions with machine learning approaches.